Renal Function, Weaning, and Survival in Patients With Ventilator-Dependent Respiratory Failure

Breaking new ground: machine learning enhances survival forecasts in hypercapnic respiratory failure

Background

The prognostic prediction of patients with hypercapnic respiratory failure holds significant clinical value. The objective of this study was to develop and validate a predictive model for predicting survival in patients with hypercapnic respiratory failure.

Methods

The study enrolled a total of 697 patients with hypercapnic respiratory failure, including 565 patients from the First People's Hospital of Yancheng in the modeling group and 132 patients from the People's Hospital of Jiangsu Province in the external validation group. The three selected models were random survival forest (RSF), DeepSurv, a deep learning-based survival prediction algorithm, and Cox Proportional Risk (CoxPH). The model's predictive performance was evaluated using the C-index and Brier score. Receiver operating characteristic curve (ROC), area under ROC curve (AUC), and decision curve analysis (DCA) were employed to assess the accuracy of predicting the prognosis for survival at 6, 12, 18, and 24 months.

Results

The RSF model (c-index: 0.792) demonstrated superior predictive ability for the prognosis of patients with hypercapnic respiratory failure compared to both the traditional CoxPH model (c-index: 0.699) and DeepSurv model (c-index: 0.618), which was further validated on external datasets. The Brier Score of the RSF model demonstrated superior performance, consistently measuring below 0.25 at the 6-month, 12-month, 18-month, and 24-month intervals. The ROC curve confirmed the superior discrimination of the RSF model, while DCA demonstrated its optimal clinical net benefit in both the modeling group and the external validation group.

Conclusion

The RSF model offered distinct advantages over the CoxPH and DeepSurv models in terms of clinical evaluation and monitoring of patients with hypercapnic respiratory failure.

Development and validation of a model for predicting the early occurrence of RF in ICU-admitted AECOPD patients: a retrospective analysis based on the MIMIC-IV database

BACKGROUND

This study aims to construct a model predicting the probability of RF in AECOPD patients upon hospital admission.

METHODS

This study retrospectively extracted data from MIMIC-IV database, ultimately including 3776 AECOPD patients. The patients were randomly divided into a training set (n = 2643) and a validation set (n = 1133) in a 7:3 ratio. First, LASSO regression analysis was used to optimize variable selection by running a tenfold k-cyclic coordinate descent. Subsequently, a multifactorial Cox regression analysis was employed to establish a predictive model. Thirdly, the model was validated using ROC curves, Harrell's C-index, calibration plots, DCA, and K-M curve.

RESULT

Eight predictive indicators were selected, including blood urea nitrogen, prothrombin time, white blood cell count, heart rate, the presence of comorbid interstitial lung disease, heart failure, and the use of antibiotics and bronchodilators. The model constructed with these 8 predictors demonstrated good predictive capabilities, with ROC curve areas under the curve (AUC) of 0.858 (0.836-0.881), 0.773 (0.746-0.799), 0.736 (0.701-0.771) within 3, 7, and 14 days in the training set, respectively and the C-index was 0.743 (0.723-0.763). Additionally, calibration plots indicated strong consistency between predicted and observed values. DCA analysis demonstrated favorable clinical utility. The K-M curve indicated the model's good reliability, revealed a significantly higher RF occurrence probability in the high-risk group than that in the low-risk group (P < 0.0001).

CONCLUSION

The nomogram can provide valuable guidance for clinical practitioners to early predict the probability of RF occurrence in AECOPD patients, take relevant measures, prevent RF, and improve patient outcomes.

Explainable Machine Learning to Predict Successful Weaning of Mechanical Ventilation in Critically Ill Patients Requiring Hemodialysis

Lungs and kidneys are two vital and frequently injured organs among critically ill patients. In this study, we attempt to develop a weaning prediction model for patients with both respiratory and renal failure using an explainable machine learning (XML) approach. We used the eICU collaborative research database, which contained data from 335 ICUs across the United States. Four ML models, including XGBoost, GBM, AdaBoost, and RF, were used, with weaning prediction and feature windows, both at 48 h. The model's explanations were presented at the domain, feature, and individual levels by leveraging various techniques, including cumulative feature importance, the partial dependence plot (PDP), the Shapley additive explanations (SHAP) plot, and local explanation with the local interpretable model-agnostic explanations (LIME). We enrolled 1789 critically ill ventilated patients requiring hemodialysis, and 42.8% (765/1789) of them were weaned successfully from mechanical ventilation. The accuracies in XGBoost and GBM were better than those in the other models. The discriminative characteristics of six key features used to predict weaning were demonstrated through the application of the SHAP and PDP plots. By utilizing LIME, we were able to provide an explanation of the predicted probabilities and the associated reasoning for successful weaning on an individual level. In conclusion, we used an XML approach to establish a weaning prediction model in critically ill ventilated patients requiring hemodialysis.

The Combination of SOFA Score and Urinary NGAL May Be an Effective Predictor for Ventilator Dependence among Critically Ill Surgical Patients: A Pilot Study

BACKGROUND

Ventilator dependence (VD) has been considered as a serious complication in critically ill patients in the intensive care unit (ICU). Acute kidney injury (AKI) is associated with VD as a result of lung-kidney interaction. The aim of our study was to investigate novel biomarkers in predicting ventilator dependence in critically ill surgical patients.

METHODS

Patients who were admitted to surgical ICU were enrolled and their serum and urine samples were collected. Novel biomarkers including gelatinase-associated lipocalin (NGAL), calprotectin, kidney injury molecule-1 (KIM-1), cystatin C, and growth differentiation factor 15 (GDF-15) were analyzed and correlated with clinical outcome.

RESULTS

A total of 33 patients were enrolled and analyzed. The majority of them received abdominal surgery prior to ICU admission. Thirteen patients were classified into the VD group, while the remaining 20 were in a non-ventilator dependence group (nVD). Statistical analysis demonstrated that the following were significantly higher in the VD group than in the nVD group: serum NGAL (420.25 ± 45.18 ng/mL vs. 314.68 ± 38.12 ng/mL, p-value 0.036), urinary NGAL (420.87 ± 41.08 ng/mL vs. 250.84 ± 39.45 ng/mL, p-value 0.002), SOFA score (11.3 ± 1.5 vs. 5.6 ± 0.7, p-value 0.001), and APACHE II score (23.2 ± 2.6 vs. 13.6 ± 0.8, p-value 0.001). The area under the ROC curve (AUROC) of urinary NGAL for VD was 0.808. The combination of urinary NGAL and SOFA score could further increase AUROC for VD to 0.835.

CONCLUSIONS

The current study demonstrated the predictive capability of urinary NGAL for ventilator dependence among critically ill surgical patients. When combined with SOFA score, the predictive ability was further augmented. Further large-scale studies are warranted to validate our findings.

Transitional Percentage of Minute Volume as a Novel Predictor of Weaning from Mechanical Ventilation in Patients with Chronic Respiratory Failure

PURPOSE

Some patients with respiratory failure fail initial weaning attempts and need prolonged mechanical ventilation (MV). Prolonged MV is associated with many complications and consumption of heathcare resources. Objective weaning indices help staffs to identify high-potential patients for weaning from the MV. Traditional weaning indices are not reliable in clinical practice. Transitional percentage of minute volume (TMV%) is a new index of the work of breathing. This study aimed to investigate the utility of TMV% in the prediction of weaning potential.

METHODS

This study was prospectively performed including all patients with prolonged MV. Researchers recorded their demographics, TMV%, respiratory parameters, Acute Physiology and Chronic Health Evaluation II score, and laboratory data upon arrival at the respiratory care center. The factors associated with successful weaning were analyzed.

RESULTS

Out of the 120 patients included, 84 (70.0%) were successfully weaned from MV. Traditional weaning indices such as rapid shallow breathing index could not predict the weaning outcome. TMV% was a valuable parameter as patients with a lower TMV%, higher tidal volume, higher hemoglobin, lower blood urea nitrogen, and lower Acute Physiology and Chronic Health Evaluation II scores had a higher rate of successful weaning. TMV%, tidal volume, and HCO3- levels were independent predictors of successful weaning, and the area under the curve was .79 in the logistic regression model.

CONCLUSION

TMV% is a novel and effective predictor of successful weaning. Patients with lower TMV% had a higher MV weaning outcome. Once patients with a high potential for successful weaning are identified, they should be aggressively weaned from MV as soon as possible.

CLINICAL TRIALS GOVERNMENT IDENTIFIER

NCT033480.

Effect of Xueniao Capsule on Escherichia coli-Induced Acute Pyelonephritis Rats by 1H NMR-Based Metabolomic Approach

Xueniao capsule, one of the famous traditional Chinese medicine (TCM) formulas, has been proved to be effective for treating acute pyelonephritis (APN) in the clinic. However, the probable mechanisms are still unclear. This study was aimed at investigating the therapeutic effect and action mechanism of Xueniao capsule on acute pyelonephritis rats. Chemical analysis of Xueniao capsule and four different extracts was conducted by HPLC and GC-MS. 21 compounds were identified in the Xueniao capsule, and obvious chemical difference was also revealed among the different extracts by chemical analysis. Metabolomics, combined with bacteriological examination, traditional histopathology, and biochemical parameters, was used to evaluate the effects of Xueniao capsule and four different extracts. After treatment with Xueniao capsule, the bacterial count of urine was decreased and the renal lesions of APN rats were ameliorated by histopathology inspection. Levels of Scr and Ucr, IL-1α, IL-1β, IL-6, IL-10, CXCL-2, and MCP-1 were decreased significantly, and the reserving effect of Xueniao capsule was superior to the different extracts and norfloxacin. 16 endogenous metabolites related to APN model were revealed, and 12 of them could be reversed by the Xueniao capsule. ¹H NMR metabolomic results demonstrated that the formula of Xueniao capsule played the best therapeutic role on APN through regulating energy metabolism and alterations of osmotic pressure. The effect of Xueniao capsule on the APN was the synergistic actions of multiple components, which need to be further investigated in future studies.